Changelog

​

Latency improvements for the Parallel Task API

​

New integrations

• LangChain: Build AI agents with Parallel’s web research capabilities using the LangChain framework
• Vercel AI SDK: Add real-time web research to your Next.js and React applications
• Zapier: Connect Parallel to 6,000+ apps with no-code automation workflows
• n8n: Self-host automation workflows with Parallel’s APIs
• Google Sheets: Import web research results directly into spreadsheets

​

Parallel Extract API

• Compressed excerpts: Semantically filtered content based on search objective
• Full content extraction: Complete page contents in markdown format

​

Parallel FindAll API

• Finds entities (companies, people, events, locations) matching specified criteria
• Evaluates candidates against match conditions using multi-hop reasoning
• Enriches matched entities with structured data via Task API
• Returns results with citations, reasoning, excerpts, and confidence scores via Basis framework

​

Parallel Monitor API alpha

• Webhooks: Receive updates when events are detected or when monitors finish a scheduled run
• Events history: Retrieve updates from recent runs or via a lookback window (e.g., 10d)
• Lifecycle management: Update cadence, webhook, or metadata; delete to stop future runs

​

Parallel Search API now generally available

• Semantic objectives that capture intent beyond keyword matching, so agents can specify what they need to accomplish rather than guessing at search terms
• Token-relevance ranking to prioritize webpages most directly relevant to the objective, not pages optimized for human engagement metrics
• Information-dense excerpts compressed and prioritized for reasoning quality, so LLMs have the highest-signal tokens in their context window
• Single-call resolution for complex queries that normally require multiple search hops

​

Parallel Task API scores SOTA on SealQA

​

Parallel Task MCP Server

​

Core2x Processor

• Cross-validation across multiple sources without deep research level exploration
• Moderately complex synthesis where Core might fall short
• Structured outputs with 10 fields requiring verification
• Production workflows where Pro’s compute budget exceeds requirements

​

Enhanced Basis features across all Processors

• Citations: Web URLs linking to source materials
• Reasoning: Detailed explanations for each output field
• Confidence: Calibrated reliability ratings (high/medium/low)
• Excerpts: Relevant text snippets from citation sources

​

TypeScript SDK

​

Deep Research Reports

​

Expanded Deep Research Benchmarks

• Parallel Ultra achieves 45% accuracy at up to 17X lower cost
• Ultra8x achieves state-of-the-art results at 58% accuracy

• Parallel Ultra achieves an 82% win rate against reference compared to GPT-5 at 66%, while being half the cost
• Ultra8x achieves a 96% win rate

​

Webhooks for Tasks

​

Deep Research Benchmarks

​

Server-Sent Events for Tasks

​

New advanced deep research Processors

​

Auto Mode in Parallel Tasks

​

State-of-the-art Search API benchmarks

​

Parallel Web Tools MCP server in Devin

​

Tool calling via MCP servers

​

The Parallel Web Tools MCP Server

​

Source Policy for Task API and Search API

​

Task Group API in beta

​

State of the art Deep Research APIs

​

Search API in beta

curl https://api.parallel.ai/v1beta/search \
  -H "Content-Type: application/json" \
  -H "x-api-key: ${PARALLEL_API_KEY}" \
  -d '{
    "objective": "When was the United Nations established? Prefer UN'\''s websites.",
    "search_queries": [
      "Founding year UN",
      "Year of founding United Nations"
    ],
    "processor": "base",
    "max_results": 5,
    "max_chars_per_result": 1500
  }'

​

Chat API in beta

from openai import OpenAI

client = OpenAI(
    api_key="PARALLEL_API_KEY",  # Your Parallel API key
    base_url="https://api.parallel.ai"  # Parallel's API beta endpoint
)

response = client.chat.completions.create(
    model="speed", # Parallel model name
    messages=[
        {"role": "user", "content": "What does Parallel Web Systems do?"}
    ],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "reasoning_schema",
            "schema": {
                "type": "object",
                "properties": {
                    "reasoning": {
                        "type": "string",
                        "description": "Think step by step to arrive at the answer",
                    },
                    "answer": {
                        "type": "string",
                        "description": "The direct answer to the question",
                    },
                    "citations": {
                        "type": "array",
                        "items": {"type": "string"},
                        "description": "Sources cited to support the answer",
                    },
                },
            },
        },
    },
)

print(response.choices[0].message.content)

​

Basis with Calibrated Confidences

1. Citations: Web URLs linking directly to source materials.
2. Reasoning: Detailed explanations justifying each output field.
3. Excerpts: Relevant text snippets from citation URLs.
4. Confidences: A calibrated measure of confidence classified into low, medium, or high categories.

{
 "field": "revenue",
 "citations": [
   {
     "url": "https://www.microsoft.com/en-us/Investor/earnings/FY-2023-Q4/press-release-webcast",
     "excerpts": ["Microsoft reported fiscal year 2023 revenue of $211.9 billion, an increase of 7% compared to the previous fiscal year."]
   },
   {
     "url": "https://www.sec.gov/Archives/edgar/data/789019/000095017023014837/msft-20230630.htm",
     "excerpts": ["Revenue was $211.9 billion for fiscal year 2023, up 7% compared to $198.3 billion for fiscal year 2022."]
   }
 ],
 "reasoning": "The revenue figure is consistent across both the company's investor relations page and their official SEC filing. Both sources explicitly state the fiscal year 2023 revenue as $211.9 billion, representing a 7% increase over the previous year.",
 "confidence": "high"
}

​

Billing Upgrades

• Auto-reload: Avoid service interruptions by automatically adding to your balance when configured thresholds are met.
• Billing History: View prior Invoices and Receipts. Track status, amount charged, and timestamp of charges.

​

Task API for web research

from parallel import Parallel
from pydantic import BaseModel, Field

class ProductInfo(BaseModel):
    use_cases: str = Field(
        description="A few use cases for the product."
    )
    differentiators: str = Field(
        description="3 unique differentiators for the product as a bullet list."
    )
    benchmarks: str = Field(
        description="Detailed benchmarks of the product reported by the company."
    )

client = Parallel()
result = client.task_run.execute(
    input="Parallel Web Systems Task API",
    output=ProductInfo,
    processor="core"
)

print(f"Product info: {result.output.parsed.model_dump_json(indent=2)}\n")
print(f"Basis: {'\n'.join([b.model_dump_json(indent=2) for b in result.output.basis])}")

​

Python SDK

​

Flexible Processors

​

Self-Serve Developer Platform

• Run a research task from scratch or using a template from Task Library
• Generate and manage API keys for secure integration
• Manage billing details, auto-reload settings, and usage analytics
• Access comprehensive guides to learn how to use the API